Warn in Tagger.begin_training if no lemma tables are available (#4351)

spacy/errors.py

@@ -88,6 +88,13 @@ class Warnings(object):
             "loaded. (Shape: {shape})")
     W021 = ("Unexpected hash collision in PhraseMatcher. Matches may be "
             "incorrect. Modify PhraseMatcher._terminal_hash to fix.")
+    W022 = ("Training a new part-of-speech tagger using a model with no "
+            "lemmatization rules or data. This means that the trained model "
+            "may not be able to lemmatize correctly. If this is intentional "
+            "or the language you're using doesn't have lemmatization data, "
+            "you can ignore this warning by setting SPACY_WARNING_IGNORE=W022. "
+            "If this is surprising, make sure you have the spacy-lookups-data "
+            "package installed.")
 
 
 @add_codes

spacy/pipeline/pipes.pyx

@@ -30,7 +30,7 @@ from .._ml import build_text_classifier, build_simple_cnn_text_classifier
 from .._ml import build_bow_text_classifier, build_nel_encoder
 from .._ml import link_vectors_to_models, zero_init, flatten
 from .._ml import masked_language_model, create_default_optimizer
-from ..errors import Errors, TempErrors
+from ..errors import Errors, TempErrors, user_warning, Warnings
 from .. import util
 
 
@@ -501,6 +501,9 @@ class Tagger(Pipe):
 
     def begin_training(self, get_gold_tuples=lambda: [], pipeline=None, sgd=None,
                        **kwargs):
+        lemma_tables = ["lemma_rules", "lemma_index", "lemma_exc", "lemma_lookup"]
+        if not any(table in self.vocab.lookups for table in lemma_tables):
+            user_warning(Warnings.W022)
         orig_tag_map = dict(self.vocab.morphology.tag_map)
         new_tag_map = OrderedDict()
         for raw_text, annots_brackets in get_gold_tuples():

spacy/tests/pipeline/test_tagger.py

@@ -0,0 +1,22 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+import pytest
+from spacy.lang.en import English
+from spacy.lookups import Lookups
+
+
+def test_tagger_warns_no_lemma_lookups():
+    nlp = English()
+    nlp.vocab.lookups = Lookups()
+    assert not len(nlp.vocab.lookups)
+    tagger = nlp.create_pipe("tagger")
+    with pytest.warns(UserWarning):
+        tagger.begin_training()
+    nlp.add_pipe(tagger)
+    with pytest.warns(UserWarning):
+        nlp.begin_training()
+    nlp.vocab.lookups.add_table("lemma_lookup")
+    with pytest.warns(None) as record:
+        nlp.begin_training()
+        assert not record.list